Hassan Twin just started putting "Markdown" around his speech, so he would say things like "asterisk laughs asterisk". So then I told him to only speak to me in emojis at which point he just started twitching and squirming as the LLM received a bunch of characters which it couldn't articulate *ROFLMAO*
Show HN: A real time AI video agent with under 1 second of latency
261–264 of 264 posts
Re: Show HN: A real time AI video agent with under 1 second of latency
#262Earlier quoted context omitted.
Glad you liked the website it was such fun project. Getting the hug of death from HN so that might be why you're getting a worse experience, please try again :)
It was disabled yesterday due to the high traffic - but I was able to connect today and after saying hello the chat immediately kicked me off after I asked a question. So unfortunately I've not been able to test it out for more than a few seconds of the "Hello, how can I help you today?" One thing I've noticed for a lot of these AI video agents, and I've noticed it in Meta's teaser for their virtual agents as well as…
Please try it again when you get the chance! We were dealing with high load the past few days and are good to go again! Re: head movements, I totally agree; natural head movements are really important to make it feel more natural. The issue is controllability today, which is something we're working on as well!
Re: Show HN: A real time AI video agent with under 1 second of latency
#263Also to add- the one service that was fast enough on the LLM side was Cerebras. The time to first token (ttft) is incredibly fast (200-300ms) and the t/s is 2000t/s for 8B- combined making for a great conversational experience.
Re: Show HN: A real time AI video agent with under 1 second of latency
#264Why did Hassaan refer to me as Dad? Is there something you’re not telling me?